LangTrend

We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-language U.S. earnings calls in 2025. The benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.

Joint-Embedding Predictive Architectures (JEPAs) are effective for images, video, and audio, yet deterministic JEPA-style latent prediction has not become a standard objective for text encoders. We argue that this gap reflects a mismatch between squared-error latent prediction and the conditional structure of language. The key requirement is conditional concentration: given a context and target location, the target representation should lie near a single meaningful point. Local image prediction often satisfies this through spatial continuity, whereas masked text can admit multiple valid token or span completions whose representations need not share a coherent center. We formalize this mismatch through three conditions—predictability, non-collapse, and low conditional variance—and show how their failure creates centroid degeneracy and collapse pressure in text. Matched I-JEPA and T-JEPA experiments reveal the predicted sequence: mutual-information saturation and elevated target variance precede train–validation instability, effective-rank degeneration, cosine collapse, and poor downstream transfer. The same pattern appears across five independent data seeds, indicating that it is not a sampling artifact. These results do not rule out predictive learning for language; they show that text-compatible JEPA objectives must preserve multiple plausible completions rather than compress them into a single latent point.

This paper presents GEMCo, a releasable, human-written proxy for inaccessible counselling data: 86 complete German e-mail counselling conversations (728 messages), expert-authored cases and counsellor sessions with trained role-players. It is validated against a held-out reference of 124 real counselling conversations. The proxy and the real conversations are measured against each other in counsellor strategies and client emotions. The gap is detectable but small. A generative validation supports the analysis. The validation method itself generalises to any domain where real data cannot be shared but a human-made proxy can. Privacy and ethics keep real counselling data closed. GEMCo carries none by design and can be released – a first step toward language research in this domain.

Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming encoder, a temporal decoder, and a depth decoder, that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures, while causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10 ms per generation step, about 16x faster than real time, with a peak runtime memory of only 21 MB and 329 MB of on-device assets, enabling continuous streaming synthesis of 20-320 seconds of audio. This constant, small footprint replaces the linear and quadratic memory scaling of conventional transformer- and GAN-based approaches. Ablation studies validate the key architectural components, and audio quality assessment confirms that the architecture maintains synthesis fidelity while achieving efficiency gains over existing methods. Operating at a 1-billion-parameter activation size within AFM 3 Core Advanced, it improves Mean Opinion Score by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device text-to-speech system.

LLM debate is usually evaluated by final answers, but transcripts also reveal whether later turns develop new argumentative content or return to earlier claims in new wording. We study this process with \textit{prior-argument similarity}, an aggregate diagnostic comparing extracted argument units with earlier units in the same debate. In controlled eight-turn debates over 71 motions, six languages, and four model agents, Chinese is the only tested language with a consistently positive gap relative to English across three multilingual embedding models. The gap persists across agents, turn positions, regression adjustment, metric variants, extraction-length controls, a second-extractor subset, and cross-encoder tail rescoring. Manual calibration shows weak item-level alignment but a high-similarity tail enriched for substantive repetition. A diversity-aware prompt lowers prior-argument similarity across languages, yet does not significantly narrow the Chinese–English gap. These findings suggest that multilingual debate evaluation should measure argumentative development over time and report mitigation effects in both average and gap terms.

In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accuracy ($Δ_{acc}$) between existing but low-frequency xiehouyu and novel ones as an index for memorization. $Δ_{acc}$ for native speakers is very low, suggesting similar processing mechanisms. However, we found that frontier Chinese models have on average a $Δ_{acc}$ of 23.6\%, while English-centric models tested have a mean $Δ_{acc}$ of 5.1\%, suggesting that frontier Chinese models are likely trained with much larger Chinese data, thus memorizing more low-frequency xiehouyu. For novel xiehouyu, Gemini 3.1 Pro demonstrated remarkable ability with acc 92.6, which is 24\% higher than human accuracy. In xiehouyu creation, those created by LLMs receive much worse ratings than those by humans. These results suggest that claims about the reasoning abilities of LLMs may need careful re-examination considering the data contamination issue, and that LLMs' creativity in language-related tasks may still be behind human experts, at least in Chinese xiehouyu.

In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The dataset captures conversational nuance prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we evaluate leading systems including commercial speech APIs and multimodal large language models. Indic DiarBench is released as an open-access resource to advance inclusive, multilingual speech technology research for Indian languages.

The embedding of word sequences into continuous vector spaces has been one of the most important developments in Natural Language Processing in the recent past. Such embeddings have found application in areas such as Automatic Speech Recognition, Machine Translation, Sentiment Analysis and many more. This essay reviews the various mechanisms that have been proposed for the calculation of word embeddings, investigates popular toolkits and embedding matrices that are available in the public domain, and experiments with one or more selected implementations to better understand their characteristics. La représentation vectorielle continue de mots a été l'un des développements les plus importants dans le domaine du traitement automatique du langage naturel au cours des dernières années. Ces représentations ont trouvé application dans des domaines tels que la reconnaissance vocale, la traduction automatique, l'analyse des sentiments, etc. Ce travail passe en revue les différents mécanismes proposés pour le calcul de ces vecteurs de mots, étudie les kits d'outils populaires et les matrices disponibles publiquement en ligne, et expérimente avec une ou plusieurs implémentations sélectionnées pour mieux comprendre leurs caractéristiques.

Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query time. This makes RAG useful for private data, fast-changing information, and reducing hallucination, but it also means the model's answer is only as trustworthy as whatever the retriever hands it. If the knowledge base accepts writes from more than one party, an attacker needs only a handful of adversarial documents to steer the model toward a chosen wrong answer. PoisonedRAG demonstrated this: as few as five crafted documents flip an undefended system's answer roughly 90% of the time, and three natural single-stage defenses (perplexity filtering, query paraphrasing, knowledge-base expansion) leave attack success at 30% or higher. We built TriShieldRAG to close that gap. Rather than relying on one checkpoint, we place three independent, formally specified rings across the pipeline: an Ingest Guard that screens documents for lexical and statistical poisoning signatures; a Retrieval Scorer that re-ranks the retrieved set by a provenance and consistency-weighted trust score; and a Cross-LLM Consensus stage that polls three architecturally diverse language models (Claude, Mistral Small, Llama 3.2) and allows one bounded re-retrieval on disagreement. We derive the conditions under which Rings 2 and 3 are expected to work: a minority-poison assumption and an explicit provenance-tag assumption. Our reported configuration is consistent with this analysis, though we have not yet run the controlled poison-fraction sweep needed to confirm it independently. Evaluated against the non-adaptive attacker from the original PoisonedRAG, over a 5,000-document Wikipedia knowledge base with 10 target questions, the full pipeline reduces attack success rate from roughly 91% to roughly 13% while preserving accuracy on benign queries.

Prior work on AI brand visibility measures the firm: does a model recommend a company, and does that track its reputation. This study asks the question one level down, in categories where the buyer picks a person. It issued 2,400 grounded API calls in one two-hour window on 24 July 2026: 120 buyer-intent prompts, four models (GPT-5.6 Sol, Gemini 3.6 Flash, Perplexity Sonar Pro, Grok 4.5), five iterations each, four European markets and five query languages. Every response was coded for whether it named an individual professional, by a rule cascade that never consults a roster and that drops detections resolving to a same-named American city (precision 96.9%, recall 61.7%, so every rate below is a lower bound). All inference corrects for clustering within prompt: intraclass correlation 0.258, effective n 407 against a nominal 2,400. Models named an individual in 25.8% of responses. Category dominates: real estate 35.4% and car dealerships 32.9% against insurance 9.1% (chi-square 159.3, p = 5.8e-8 after correction). Models differ four-fold, from Grok 38.0% to Gemini 9.3%. Citation type predicts naming and citation volume does not: naming responses cite the individual's own site 2.6 points more often (95% CI +1.4 to +3.9) and category portals 4.3 points more often, and cite firm-owned pages at the same rate (44.1% against 45.5%). On nine matched translation pairs, English prompts named an individual in 36.7% of responses against 15.6% for the same question in the local language (OR 3.14, clustered p = 0.074, so the direction is clear and the design cannot close it). A 939-person roster built from public LinkedIn search matched 128 of 27,293 name-shaped mentions (0.47%), 26 of the 939 people were ever named, and the roster-derived rates of 0.0% to 25.4% measure that overlap. Roster-based measurement of individual AI visibility sees a small and unrepresentative slice of what models do.

This paper presents Mwando, a virtual educational assistant designed to support the teaching and preservation of shiKomori, the language of the Comoros Islands. The system covers the four main dialectal variants (shiNgazidja, shiMwali, shiNdzuani and shiMaore) through a knowledge base constructed from phrases, proverbs, dictionaries and grammar lessons. A multi-agent architecture combining vector search, a knowledge graph and web search fallback enables accurate and context-aware responses. Evaluation on 500 queries demonstrates strong performance on vocabulary lookup and grammar explanations, while qualitative case studies illustrate both capabilities and current limitations. This work represents an initial step toward computational support for shiKomori and provides a blueprint for developing AI-powered educational tools for other low-resource languages.

Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin with rough strokes and refine them over time, whereas existing methods typically require their conditioning representation to be fully specified before generation, a fundamental mismatch with how design actually works. Second, the 2D floor plan is not an optional intermediate but an irreplaceable spatial contract. Once room boundaries, doors, and windows are fixed, furnishing reduces from open-ended spatial reasoning to bounded constraint satisfaction. Bypassing this contract, as existing 3D systems do by delegating layout to language models, yields overlapping rooms and implausible proportions; directly calling general-purpose language models likewise produces geometrically invalid layouts. Guided by these insights, we present PlanCraft. SketchPlan supplies the missing training signal by replaying the architect's drawing process on 80K real floor plans, producing partial sketches at every completeness level. PlanCraft-Diff progressively sharpens an incomplete sketch into a geometrically precise, vectorizable floor plan through a coarse-to-fine strategy. With the spatial contract established, PlanCraft-Agent then furnishes the scene within well-defined room boundaries. Experiments show that PlanCraft achieves a 61.1\% lower FID than the best existing 2D method and surpasses existing 3D systems by 15 points in expert-rated spatial rationality, with a sketch at only 25\% completion already outperforming all fully specified baselines.

Offensive language detection models generally suffer performance degradation when deployed across datasets and across languages, yet most existing studies stop at reporting this phenomenon and lack a systematic methodology for decomposing the causes of degradation into attributable components and quantifying the cost of remediation. This paper proposes a diagnosis and optimization framework composed of three coordinated technical components. First, a zero-shot transfer loss decomposition that separates the performance degradation from OLID to MLMA into two independently measurable components, namely dataset effect and language effect. Second, a controlled fine-tuning protocol that quantifies both adaptation efficiency and the hidden damage inflicted on the source task by comparing few shot learning curves under continued fine-tuning and cold-start starting points. Third, three joint training strategies incorpo rating temperature sampling and experience replay, which offer a controllable Pareto trade-off between improving multilingual capability and preserving source-task performance. Experiments built on this framework show that the dataset effect dominates the zero-shot transfer loss and substantially outweighs the language effect. Few-shot adaptation without a replay mechanism, though data-efficient, inflicts source task damage 4 to 9 times greater than that of the joint training strategies, and its damage magnitude is highly unstable. The three joint training strategies trade 3.2 to 4.1 percentage points of source-task performance for 8.1 to 42.6 percentage points of multilingual capability gain, forming a clear and controllable Pareto trade-off.

Large Language Models (LLMs) have transformed conversational AI, yet high-quality multilingual code-mixed dialogue resources remain scarce, particularly for Indic languages where speakers naturally alternate between English and their native language in both native-script and Romanized forms. We present IndicTalk, one of the largest multilingual Indic code-mixed conversational corpora, comprising over 13,28,604 event-grounded multi-turn conversations across 18 language varieties covering 9 Indic languages. The corpus is generated through a fully automated pipeline that combines real-world news grounding, persona-conditioned dialogue generation using multilingual LLMs, and automatic quality validation. Extensive linguistic, automatic, and human evaluations demonstrate that IndicTalk produces fluent, coherent, and naturally code-mixed conversations across both script variants. We will release IndicTalk to support the development and evaluation of multilingual conversational AI for underrepresented Indic languages. The dataset is available at: https://huggingface.co/datasets/LingoIITGN/IndicTalk .

Vision-Language Models (VLMs) are demonstrating significant capabilities in medical tasks like radiology analysis, yet providing faithful and interpretable explanations remains a key consideration for their responsible deployment in clinical settings. However, existing explanation methods, such as the widely used FIxLIP framework, often struggle with the fine-grained nature of modern tokenizers. The tokenization problem fragments clinical concepts—splitting terms like "saddle embolus" into scattered, meaningless subwords—which leads to noisy, semantically incoherent cross-modal attributions. Such fragmentation also results in a combinatorial explosion of interaction possibilities, obscuring the model's true reasoning. To address this, we introduce ParseFIxLIP, an extension that incorporates the Tree-Gram Parsing into the Banzhaf interaction game used by FIxLIP. This semantically informed strategy utilizes dependency parsing trees to define explanation players by grouping related text tokens into semantically coherent units. Our smart_depth grouping strategy, merging tokens according to spaCy token dependency tree, successfully mitigates concept fragmentation, yielding substantially more interpretable cross-modal interactions by unifying complex medical concepts. Quantitatively, while baselines struggled with the high dimensionality of long captions, our parsing approach maintained statistical robustness and semantic parsimony. Qualitative analysis on BiomedCLIP, validated on medical imagery (ROCOv2) and general examples, confirms that the approach accurately captures the synergistic influence of grouped words on model predictions. In conclusion, our work offers intuitive and clinically relevant insights into VLM decision-making, fulfilling the critical need for coherent explanations in the medical domain.

Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence. However, most existing static benchmarks risk contamination: they primarily consist of outdated claims verifiable using an LLM's internal knowledge without external evidence. This can inflate performance estimates and fail to reflect true capability on novel claims that require up-to-date information. To address this, emerging dynamic benchmarks collect claims published after LLMs' knowledge cut-off dates, assuming they are uncontaminated. This work revisits this assumption by empirically studying contamination risks in both the state-of-the-art (SOTA) static AVeriTeC benchmark and our newly constructed dynamic ClaimReview2025Q4 benchmark, as well as their impact on MAFC evaluation. Our experiments yield 16 findings, highlighting three key results: (1) Dynamic evaluation reduces but does not eliminate contamination risks, as 17.09\%–29.30\% of post-cut-off claims remain potentially contaminated; (2) Many newly published claims can be verified either directly or by synthesizing multiple pieces of public knowledge available before the cut-off; and (3) Contamination can induce statistically significant inflation in MAFC performance, increasing Macro-F1 by up to 11.34 points and distorting system rankings. In light of these findings, we re-evaluate SOTA LLMs under a strictly contamination-controlled setting. Our study provides practical guidelines for trustworthy MAFC evaluation.

Despite recent advances in large language models (LLMs), their ability to generate empathetic mental health counseling responses in low-resource languages remains largely unexplored. To address this gap, we curate 625 authentic mental health cases from three complementary sources: (1) publicly available Facebook posts discussing mental health concerns, (2) transcripts from the Bangladeshi television program "Ami Akhon Ki Korbo", and (3) anonymized student questionnaire responses covering diverse emotional and psychological challenges. Based on these cases, we build an evaluation corpus comprising advice written by licensed clinical psychologists and responses generated by three modern proprietary LLMs: GPT-4o Mini, Claude 4.5 Haiku, and Gemini 2.5 Pro. We further propose the Role-Playing Reflective Chain-of-Thought Advisory Framework (RP-RCAF), a task-specific prompting strategy that combines expert-authored few-shot examples with structured self-reflection to produce supportive, culturally aware, and ethically aligned counseling through a compassionate advisor persona. We also introduce the Grok 4-Based Response Evaluation and Scoring Framework (G-REFS), which integrates automated assessment with expert psychologist validation across emotional sensitivity, cultural appropriateness, linguistic clarity, and ethical soundness. Experimental results show that RP-RCAF consistently outperforms conventional prompting across all evaluated models and produces responses that more closely align with professional psychological counseling.

Named Entity Recognition (NER) for low-resource languages such as Marathi remains a challenging task due to limited annotated resources and linguistic complexity. Although recent Large Language Models (LLMs) have demonstrated strong performance across a wide range of natural language processing tasks, their effectiveness for language-specific NER in low-resource settings remains uncertain. In this study, we fine-tune MahaBERT-v2 on different variants of the MahaNER dataset and systematically compare the performance of these models with an existing MahaNER baseline and prominent general-purpose LLMs, including Gemini, LLaMA-3.3-70B, and Gemma models. All models are evaluated on a Marathi NER test dataset using standard metrics of precision, recall, and F1-score. The experimental results show that the fine-tuned MahaBERT-based models consistently outperform both the baseline and all evaluated LLMs, with the fine-tuned models achieving F1-scores ranging from 0.88 to 0.91, surpassing the existing MahaNER model (0.8843) and significantly exceeding the performance of LLM-based approaches, whose F1-scores range from 0.57 to 0.69. These findings demonstrate that task-specific, language-focused models trained on domain-relevant data remain more effective than general-purpose LLMs for Marathi NER, highlighting the continued importance of specialized architectures for low-resource language processing.

A small language model can receive the governing statutory provision and still answer incorrectly. We test whether fine-tuning on examples containing relevant law improves later use of retrieved law. We curate 2{,}165 bilingual QA records from six Bangladeshi acts and three schedules, then fine-tune Qwen3.5 at 0.8B, 2B, and 4B. Evaluation uses the 2022 and 2023 Bangladesh Bar Council exams in Bangla and machine-translated English, with no retrieval, BM25, or FAISS, scored by strict consistency over three seeded runs. At 0.8B, fine-tuning raises the 2022 English FAISS score from 2 to 34 of 100. Gains at 0.8B and 2B survive paired testing, but the 4B model has no detectable net gain: Bangla improves while several English conditions regress. Fine-tuning also reduces answers that drift from Bangla into mostly English from 44.0–53.2\% to 0.2–0.7\%, with adjusted $p<.001$ at every scale. Retrieval quality is therefore not the only bottleneck. Small bilingual legal models also differ in how they use supplied law and whether they answer in the requested language. The dataset is publicly available at https://huggingface.co/datasets/momahadi/bangladesh-legal-qa-dataset.

Large language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data. Existing semantic query processing systems invoke request-centric LLM serving systems that are unaware of the query plan, leaving substantial performance opportunities unused. This paper introduces relational LLM serving, an abstraction that makes LLM serving aware of semantic query structure while preserving query semantics and output accuracy. The key opportunity is pipelined execution across semantic operators: when intermediate tuples flow directly from one operator to the next, their KV-cache state can be reused instead of recomputed. We present Kalypso, a relational LLM serving system that exposes an API for semantic query plans and executes them using an adaptive, memory-aware scheduling algorithm. Kalypso addresses a new online scheduling problem in which pipelined operator execution is coupled with GPU memory pressure management to reuse KV-cache state in the serving engine before eviction. Its scheduler continuously adjusts memory allocations to balance upstream parallelism, downstream progress, and GPU utilization. Our evaluation shows that Kalypso improves query completion time over baselines using request-centric LLM serving, with speedups up to 4.57x across diverse workloads, demonstrating that query-aware LLM serving can substantially improve the efficiency of semantic query execution.

Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land somewhere, and what counts is how far, and in which directions, its answers can be steered. That steering runs through the system prompt: the personalization layer a platform sets, or one induced from a user's history, not necessarily written by hand. We run a dispersion-first stress test of prompt-based controllability across 12 ideological personas plus an unsteered baseline, 70 Political Compass items, ten replicates, and seven leading LLMs: GPT-5, Claude, Grok, Gemini, DeepSeek, Kimi, and Qwen (63,700 responses). Contextual framing explains roughly 88%-93% of variance on the economic and society axes, model identity under 3%: responses are highly instruction-adjustable. Models do not shift alike: some move more, and some saturate under extreme framings. Conflicting directional-steering results in prior audits resolve once baselines are recognized as non-centered: displacement and proximity diverge, so the effect is geometric, not differential compliance. Under authoritarian prompts, models produce similar shifts on the same questions. Political-coordinate audits therefore need steerability audits reporting dispersion, symmetry, saturation, and refusal floors. We release prompts, benchmark data, and code.

Chain-of-thought (CoT) explanations support oversight only if they are faithful: the stated reasoning must actually produce the answer. Auditing black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations, we find answer correctness structures the problem at every level. Answer incorrectness alone (an oracle diagnostic, not a deployable detector) outperforms every purpose-built signal (AUROC 0.696), because 69% of annotated unfaithfulness occurs on incorrect answers. Stratifying by correctness splits detection into two regimes: on correct answers, behavioral signals moderately separate faithful from post-hoc reasoning (0.63-0.67); on incorrect answers, where most unfaithfulness lives, no tested signal is detectably above chance (replicated on all four models for benchmark-wide signals). The standard step-removal metric anti-correlates with human labels; this inversion reproduces on the benchmark's released scores and on hint-dependent counterfactually labeled traces. Linear probes decode the behaviorally blind regime in Llama-3.1-8B and the correct-answer regime in Qwen-2.5-7B, with no shared, positively aligned direction detected across regimes; instructed answer-first traces (7 models) transfer to neither annotated regime, while hint-induced unverbalized answer flips do, in model- and source-dependent settings. We also independently verify and resolve a documentation-data mismatch in the benchmark's label semantics.

Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Once user intent becomes predictable, an intent readiness detector triggers LLM-based generation of a short prefatory response. Concurrently, a voice activity projection (VAP) model determines when to deliver it. Through a field experiment with a route-guidance robot in a shopping mall, we evaluated three conditions: no-filler, fixed-filler, and contextual-preface. Both fixed-filler and contextual-preface significantly reduced initial response latency relative to no-filler. Relative to fixed-filler, contextual-preface had significantly longer initial response latency but a significantly shorter initial-to-main gap. Exploratory ratings showed no significant differences. These results indicate a timing trade-off.

Over fourty years after the initial publication of "Implications of Theories of Language for Information Systems" in MIS Quaterly, Lyytinen reflects about the origins of his publication and the developments in this area of research over the past decades. In the here presented interview, Lyytinen discusses the linguistic core of information systems also in light of recent trends and developments in the field, especially with regards to large language models and generative AI. Future research directions following a linguistic perspective on Information Systems (IS) research are outlined.

Large language models show strong promise for information extraction (IE), but existing reflection-based correction methods are often misaligned with structured extraction outputs. Free-form self-reflection can flag an error, yet it rarely identifies whether the failure is a missing span, wrong label, boundary mismatch, invalid relation type, or reversed argument order. We introduce LA-RL (Label-Aware Reflective Reinforcement Learning), an outcome-supervised framework that guides IE self-correction with task-grounded diagnostic labels. A single backbone first predicts an extraction, diagnoses task-specific error labels, and then revises its output conditioned on the diagnosis. Training starts from diagnostic data labeled by an annotation model for cold-start supervised fine-tuning and proceeds through two GRPO stages that reward final extraction quality, format validity, and first-pass correctness, without a process reward model. Experiments on named entity recognition, relation extraction, and event extraction show consistent same-backbone gains over SFT, including 6.83 average F1 on SciER relation extraction, about 20 F1 on out-of-distribution relation extraction, and 14.80 trigger F1 plus 17.50 argument F1 on DuEE1.0. Ablations show that reflection structure is task-sensitive: stronger constraints benefit relation extraction, whereas named entity recognition needs less restrictive correction under domain shift.

Gender-inclusive language generation seeks to transform biased text into inclusive alternatives while preserving semantic meaning and contextual coherence. This paper presents the IHLC system for the LT-EDI 2026 Shared Task, addressing both gender-inclusive rewriting and counter-narrative generation. For gender-inclusive rewriting, we employ parameter-efficient Low-Rank Adaptation (LoRA) fine-tuning, achieving an official score of 80.00%. Our primary contribution is a compute-efficient inference-time representation engineering approach for counter-narrative generation. We derive a principal steering direction from contrastive hidden-state activations using principal component analysis (PCA) and inject it into the intermediate representations of Gemma-3-4B-it during inference, enabling behavioral steering toward inclusive responses without modifying model weights. Combined with constrained prompting, this approach produces polite and contextually appropriate counter-narratives, achieving an official score of 78.12%. We further present a manual analysis of steering behavior, identifying key failure modes including semantic drift, residual bias leakage, layer sensitivity, over-steering, and text degeneration. Our findings highlight both the practical potential and current limitations of activation steering as a lightweight alternative to parameter updates for controllable and socially aligned language generation.

Instruction tuning has become the standard method for adapting large language models to follow human intent, yet existing instruction datasets are dominated by English-language general-knowledge tasks and lack coverage of specialized pedagogical domains. This paper presents IKS-Instruct, a dataset of 24,795 instruction-response pairs for teaching language models to deliver educational content grounded in Indian Knowledge Systems (IKS). The dataset spans seven languages (English, Hindi, Sanskrit, Tamil, Telugu, Kannada, and Malayalam), covers 41 pedagogical techniques from the Vedic oral and mathematical traditions, and is aligned with the Central Board of Secondary Education (CBSE) curriculum for classes 6 through 12. The pairs are derived from six source types: classical text corpora (Bhagavad Gita, Thirukkural, Sangam literature, Vedic texts), curriculum-aligned pedagogical templates, Vedic mathematical sutra demonstrations, bilingual instruction pairs, technique-grounded multi-turn dialogues, and cross-tradition comparative analyses. Quality is assessed through a multi-judge evaluation framework in which independent language models score responses on 12 dimensions including technique fidelity, pedagogical quality, factual accuracy, and IKS cultural depth. Under a uniform five-judge external panel (median aggregation over 1,201 stratified items), the strongest IKS-Instruct fine-tune of a compact 7B model reaches a median judge score of 6.39, within 0.15 of a strong general-purpose reference model (Nemotron-Nano at 6.54) at a fraction of its deployment cost, while the base model without IKS fine-tuning scores near zero on the IKS-specific dimensions. Model quality does not increase monotonically with data curation, a result we report together with the corresponding data-quality gains.

Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages. Sanskrit, Tamil, and other classical Indic languages exhibit agglutinative morphology, productive sandhi (phonological fusion at word boundaries), and domain-specific vocabularies absent from general-purpose training data. This paper presents BHARATI, a set of SentencePiece BPE tokenizers trained on a balanced 781 MB corpus spanning seven languages (English, Hindi, Sanskrit, Tamil, Telugu, Kannada, and Malayalam) with native script support for all languages. We describe three successive tokenizer versions: v1 (English and Sanskrit only, with broken byte-fallback for Tamil), v2 (four-language support with byte-level fallback for southern languages), and v3 (full seven-language native subword coverage). Subword fertility analysis demonstrates that v3 averages 2.6 tokens per Indian Knowledge System (IKS) technical term, compared to 5.25 tokens per term with GPT-2's tokenizer and 3.75 tokens with the multilingual SentencePiece baseline, with the largest gains on a set of reserved IKS terms that are represented as single tokens by construction. On a held-out test set of 490 IKS-domain sentences (70 per language across seven languages, released with the measurement script), v3 reduces sequence length by roughly 90% relative to GPT-2 and byte-level encoding (which lack native Indic subwords) and by approximately 25% relative to the mBART-50 multilingual baseline, averaged across the six Indic languages, directly translating to increased effective context length for downstream language models. The tokenizer models (32,000 vocabulary), training scripts, and evaluation benchmarks are released under open licenses.

Cross-lingual mismatch remains a key source of overall degradation in modern speaker verification. The TidyVoice2026 Challenge targets this setting with text-independent verification, comprising 3,666 training and 808 development speakers in 40 languages and 2,200 evaluation speakers in 38 unseen languages, without language labels at test time. Starting from the official SimAM-ResNet34 baseline pretrained on VoxBlink2 and VoxCeleb2 and fine-tuned on TidyVoice, we revisit Nuisance Attribute Projection (NAP) as a simple language-normalization step in the embedding space. We estimate a compact language subspace from cross-language same-speaker differences and project embeddings onto its orthogonal complement before cosine scoring with Adaptive Symmetric score normalization. This reduces development EER from 2.97\% with cosine and 2.70\% with AS-Norm to 2.18\% and yields a Codabench evaluation score of 8.40, showing that simple back-end language normalization can rival more complex systems.

Mathematical Word Problems (MWPs) are an important benchmark for evaluating natural language understanding and quantitative reasoning. Despite recent progress in high resource languages, Bengali remains underexplored due to the limited availability of large scale annotated datasets. In this work, we introduce PatiGonit22K, an expanded Bengali MWP dataset containing 22,441 problems, developed by extending the original PatiGonit dataset with a substantially larger collection of complex mathematical problems. The dataset includes both simple and multi operation equations, providing a balanced benchmark for evaluating mathematical reasoning across different difficulty levels. Each problem is carefully translated, annotated, culturally adapted, and verified to ensure linguistic consistency and mathematical correctness. By increasing both the scale and complexity of Bengali MWPs, PatiGonit22K provides a more comprehensive resource for future research on mathematical reasoning and educational NLP applications in low resource languages.

Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior.

Existing lexical distance, similarity, and evaluation metrics operate on Unicode code points, which can misrepresent errors in writing systems where a single grapheme is represented by multiple Unicode code points. We introduce grapheme-kit, an open-source Python library that extends these metrics to operate on grapheme clusters instead. The library also provides improved grapheme processing for Tamil and Sinhala, including accurate grapheme cluster identification and grapheme composition/decomposition utilities. Through an OCR case study, we demonstrate that grapheme-level metrics provide a more faithful evaluation of complex scripts.

We present a systematic study of healthcare-domain cross-lingual transfer to address the scarcity of biomedical NMT resources for Arabic-script languages. We use Arabic and Persian as higher-resource pivots to improve translation for \textbf{four severely low-resource} targets: Dari (Afghan Persian, a standardised variety of Persian), Pashto, Sorani Kurdish (Central Kurdish, a major standardized variety of Kurdish), and Urdu (closely related to Hindi). Using LoRA fine-tuning on small decoder-only LLMs, we train \textit{domain-specific pivot adapters} and evaluate \textbf{three transfer strategies}: few-shot in-context learning, minimal supervised adaptation, and, to the best of our knowledge, for the first time in this setting, zero-data LoRA adapter merging. Supervised adaptation with just 500 sentences achieves near pivot-language quality for Dari (CHrF++ 41.01) and meaningful gains for Urdu (28.88), while adapter merging reaches within 3.5 CHrF++ of supervised adaptation for Dari at zero additional cost. Pashto and Sorani Kurdish remain insufficient for high-stakes clinical deployment exposing the limits of cross-lingual transfer when structural distance from the pivots is too great. LoRA adapter merging works surprisingly well for closely related languages, even without target-language biomedical data.

Instruction hierarchy (IH) requires models to prioritize instructions by source, ensuring that higher-priority instructions override lower-priority ones. Despite its importance for safe and controllable deployment, existing evaluations have focused almost exclusively on English, leaving it unclear whether IH compliance remains stable in multilingual settings. We introduce XIH-Bench, a benchmark for multilingual IH evaluation with both same-language and cross-language conflicts across six languages, four domains, and three IH settings. Across models, we find two consistent patterns. First, IH compliance exhibits a clear language-dependent asymmetry: a language that strengthens compliance in the higher-priority position can become disruptive in the lower-priority position. Second, cross-language conflicts yield higher compliance than same-language conflicts, a phenomenon we term the Language Boundary Effect. We further show that language specialization can make lower-priority instructions in model-favored languages harder to override, creating multilingual reliability and security risks.

Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12–52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.

Recent work has shown that subword vocabularies can be trained to optimize compression for a specific inference rule rather than relying on greedy heuristics such as Byte Pair Encoding (BPE). We extend this approach to greedy left-to-right longest-match decoding, the fast and widely used inference rule underlying WordPiece. We introduce Joint Optimization for Greedy Longest-Match Tokenization (JOLT), which formulates vocabulary learning as an integer program over vocabulary-selection and segmentation-choice variables. Greedy-consistency constraints ensure that each optimized segmentation exactly matches the segmentation produced by longest-match decoding under the selected vocabulary, aligning the training objective with deployment-time tokenization. To scale the optimization, we solve a linear programming relaxation and selectively introduce higher-order segmentations only for unresolved pretokens. The resulting relaxation is nearly integral: rounded solutions fall within 0.008 - 0.176 % of the LP lower bound on the training scope. The bound also shows that BPE is already within 1 - 2 % of the best achievable compression under greedy longest-match decoding, while JOLT closes 89.6 - 99.4 % of the remaining gap. On held-out validation data across four training scopes and vocabulary sizes of 32,000 and 64,000, JOLT produces up to 0.78 % fewer tokens than BPE, with improvements generally increasing as the training scope grows. These results demonstrate that inference-aligned vocabulary optimization can recover most of the limited compression headroom left by BPE while providing a certificate of near-optimality.

Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM prediction. Using Japanese speed-dating conversations, we combine predictions from a transcript-only LLM and a supervised speech predictor to estimate participants' reported liking of their partners. We show that speech can complement transcript-only LLM prediction, but that this complementarity is conditional rather than universal. Combining the two predictions significantly improves pairwise ranking accuracy over the transcript-only LLM alone in all evaluated conditions. By contrast, gains in per-participant Pearson $r$ vary across conversation rounds and rating directions, with none significant after correction. Retrospectively, these $r$ gains are concentrated among participants for whom the speech predictor is more accurate. Speech can therefore retain predictive value even when an LLM predicts attraction from transcripts. The relevant question is not simply whether speech helps, but where its complementarity emerges.

There is a growing need for reliable and culturally validated instruments to assess psychological dependency on large language models (LLMs), particularly as LLMs are increasingly used for task execution, decision-making, and communication in organizational and work-related settings. This need is especially relevant for Spanish-speaking populations, where LLM adoption is rapidly expanding, yet validated psychometric tools remain scarce. The present study reports the first validation of the Spanish version of the Large Language Model Dependency Scale (LLM-D12-SP), extending prior validations conducted in English- and Arabic-speaking samples. The LLM-D12 is a two-dimensional instrument assessing Instrumental Dependency (reliance on LLMs for performing tasks and supporting decisions) and Relationship Dependency (psychological reliance on LLMs for companionship and social interaction). A total of 386 Spanish-speaking participants (M = 28.0 years, SD = 6.1; 55% male) completed the LLM-D12-SP. Confirmatory factor analysis supported the original two-factor structure. The scale demonstrated good internal consistency (Cronbach's alpha = 0.89 total; 0.86 Instrumental; 0.85 Relationship). Discriminant validity analyses indicated that the two subscales represent related but distinct constructs. External validation showed that both dependency dimensions were positively associated with internet addiction and perceived trustworthiness of LLMs, while showing weak or no association with need for cognition. Together with prior English and Arabic validations, these findings establish cross-linguistic support for the scale's structure and provide a psychometrically sound tool for investigating psychological aspects of LLM use in organizational contexts.

We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi. Financial certification exams such as the CFA, EFPA, and CPA demand structured domain reasoning that standard NLP benchmarks do not capture, and this challenge compounds across languages where retrieval and representation infrastructure is underdeveloped. We build a retrieval-augmented pipeline on LangGraph that detects query language and retrieves semantically relevant exemplars from a 30,209-entry multilingual knowledge base using BGE-M3 embeddings and FAISS indexing. The system then scores answers via Retrieval-Augmented Direct Scoring (RADS), reading next-token log-probabilities over candidate option letters rather than generating free-form output. For low-resource languages, we fuse per-language and cross-lingual retrieval indices using weighted Reciprocal Rank Fusion. Model selection is language-routed: Qwen3-14B for Arabic, Chinese, and Hindi; Qwen2.5-14B for English; and Llama-3.1-8B for Greek, a routing derived from empirical ablations that reveal substantial language-asymmetric performance gaps. Notably, chain-of-thought prompting significantly degrades Greek accuracy (90.7% to 20.9%), and enabling Qwen3's default thinking mode collapses Arabic RADS performance to near-chance levels. Our results indicate that effective multilingual financial reasoning requires language-aware retrieval, model routing, and deliberate scoring strategy selection.

We propose CHiPS, a lightweight character-level authorship attribution method for Romanian texts. All reported experiments are closed-set: the true author is one of the candidate authors in the training data. CHiPS studies two complementary fingerprints of writing style: CH-SVM, a character-histogram classifier based on one-character marginal distributions, and FFT12-LR, a positional-signal classifier that represents selected characters and punctuation classes as impulse trains (binary indicator sequences over character positions) and extracts Fourier/Welch spectral descriptors. We also report CHiPS-F, a leakage-safe decision-level fusion variant, and an optional top-5 listwise reranker trained only on out-of-fold predictions. The method requires no tokenization, syntactic analysis, pretrained language model, or transformer fine-tuning, and it avoids character $n$-gram features with $n \geq 2$ in the histogram component. On a locked grouped ROST split comprising 400 files from 392 source-text groups, written by 10 authors, with source-text-level evaluation and grouped five-fold model selection, CHiPS-F reaches 0.9310 accuracy and 0.9341 macro-F1. A matched but unrestricted character 2–5-gram TF–IDF SVM comparator reaches 1.0000 accuracy and macro-F1 on the same held-out groups, so the contribution is not a claim of best possible classification accuracy. Instead, the experiments ask how far restricted, transparent character evidence can go under strict leakage control. On ROSTories-cleaned, a secondary ROST-overlapping corpus comprising 1,248 files from 1,240 source-text groups, written by 19 authors, the same protocol gives 0.8919 accuracy and 0.8708 macro-F1 for CHiPS-R.

Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for tasks like ASR and spoken question answering. Existing systems, however, typically only support a few languages and are often limited to English. We introduce MEUSLI, the first open-science multilingual projector family that links a Whisper encoder with open-source multilingual LLMs, enabling fully open-source end-to-end ASR in 28 European languages. MEUSLI extends prior monolingual pipelines, delivering strong results across high- and low-resource languages. Using proper continual leaning techniques, MEUSLI can be easily extended to other languages not seen in training. We further demonstrate that the MEUSLI projector can be leveraged beyond ASR, enabling multilingual speech translation and topic identification with only a few hours of task specific supervision per language. Overall, MEUSLI provides a solid foundation for multilingual speech understanding tasks, supporting scalable and inclu- sive open-source SpeechLLM

A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode where frontier models exhibit invisible reasoning by leveraging semantically irrelevant filler tokens to improve performance on synthetic reasoning tasks. We evaluate 13 frontier language models across three tasks and find that many models benefit significantly from filler tokens, with accuracy improvements of up to 13 percentage points. The benefit depends on which tokens are used and differs across models. We further show that filler tokens enable Claude Opus 4.5 to satisfy a hidden modular arithmetic constraint without sacrificing accuracy on its primary task, demonstrating that invisible reasoning can serve objectives entirely invisible to CoT monitoring. Reinforcement learning gives Qwen3-235B strong preferences over filler token content, but neither RL nor supervised fine-tuning produces a filler token benefit that persists at test time. Our results indicate that frontier models already perform consequential computation with no interpretable trace in their output tokens.

Mastodon as a decentralized federation of independently moderated social servers poses unique challenges for the detection and mitigation of toxic content. There are no unified moderation standards. The ecosystem is very diverse and uneven. This paper explores the development and spread of toxicity in Mastodon, utilizing machine learning methods to examine user posts. The results offer clarity on toxicity trends and its implications for community health and decentralized governance.

Self-harm content is particularly challenging to detect using NLP techniques, and is also a high-stakes task which requires the highest accuracy to enable timely intervention or flagging at-risk users. We therefore present an analysis of how LLMs represent such self-harm content, which has downstream applications in self-harm detection, LLM intervention and governance and policing. In this paper, we focus on two datasets and four models, and perform two main experiments: (1) We train and evaluate linear probes across all layers of each model on two self-harm datasets: X-Sensitive and SH-Detection. Across both corpora, self-harm information crystallizes in the final 3 - 7% of network layers (93 to 97% depth). (2) We extract contrastive self-harm directions and, after performing a normaliation step, we find that the most accurate probes are not necessarily the most linearly separable. In particular, we find Gemma-3-4B to represent this \textit{contrastive self-harm direction} in a slightly different, more intricate way than the other LLMs.

Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language. We evaluate five recent models on programming problems in Python, Java, Rust, and OCaml. We carefully control for problem difficulty, and show that there can be stark variation in token consumption that is consistent across models. To understand why, we analyze both the structure and content of agent trajectories. First, we re-execute every intermediate solution and abstract each trajectory as a sequence of test-outcome vectors, then label the work between successive solutions. This reveals agents repeatedly producing noncompiling solutions in unfamiliar languages and revising solutions that already pass. Second, we analyze trajectory text, finding that agents plan solutions in code comments, distrust the provided tests in favor of inputs they invent, and sidestep unfamiliar target languages by prototyping in Python. Our results show that by-language token efficiency is a metric that should be considered when benchmarking and developing multilingual agents, and, for the tokenmaxxer, a guide to the most expensive language to work in.

Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferation of large language models (LLMs) throughout all areas of life, recent work suggests that interacting with LLM agents can be instrumental within the field of SLA and foreign language education, especially for reducing FLA. Related work also suggests that linguistic demands and task complexity can be predictors of FLA, implying that the use of demanding, complex language could lead to learners experiencing higher FLA. In this paper, we propose a novel multi-agent embodied conversational system that generates level-appropriate dialogue for English language learners. These levels are based on those defined by the Common European Framework of Reference for Languages (CEFR) to describe non-native listener and speaker proficiency. Using a "generate-evaluate-regenerate" loop with multiple LLM agents and a level classifier, it achieves a desired simplicity that is adaptive to the user's proficiency level. We also share the results of a preliminary small-sample pilot study that tested this system with Japanese university students, to see whether it would yield lower FLA levels than an unsimplified embodied conversational agent. Analysis of conversational output showed that 87.4% of dialogue sentences generated by the proposed multi-agent system fell within one predicted CEFR level of the learner's self-assessed proficiency, compared to 54.1% for the unsimplified agent. This suggests that the novel system is better able to produce output at an appropriate level for the learner. Though this study did not yield statistically significant evidence that the system reduces FLA levels in Japanese learners of English, likely due to a small sample size, it provides usability findings and culturally-informed design insights that will inform future study.

Most endangered languages lack the parallel data required for machine translation, despite the existence of descriptive grammar books. We introduce a pipeline that uses large language models to extract grammatical rules, example sentences, and lexicons from grammar books and generate synthetic parallel corpora for fine-tuning-rather than feeding grammar content into prompts at inference time, as in prior work. Validated on three typologically diverse low-resource languages-Kalamang (Papuan), Tuatschin (Romance), and Mandan (Siouan)-we show that fine-tuning on synthetic data improves over seed-data baselines in 75% of configurations for Kalamang and 59% for Tuatschin, with best-case ChrF++ gains of +8.8, +5.3, and +3.3 respectively. Through a systematic factorial study across 96 configurations varying target part-of-speech, retrieval granularity, and sample volume, we identify which factor combinations drive gains and where they break down. Our results demonstrate that static linguistic documentation can be repurposed for machine translation fine-tuning, offering a practical path towards translation tools for severely under-resourced languages.

Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from inter-speaker variability. To address this critical issue, we present the first patient-independent multimodal depression detection framework that incorporates domain generalization (DG), jointly leveraging both acoustic and textual modalities. The proposed model integrates bidirectional Long Short-Term Memory (BiLSTM) with intra- and cross-modal attention mechanisms, accompanied by segment-level fusion for decision-making. Generalization is further enhanced by applying a gradient reversal layer inspired by Domain-Adversarial Training of Neural Networks (DANN), which promotes domain-invariant representations by adversarially limiting the model's ability to identify individual speakers, effectively reducing patient-specific bias. Conducting experiments on the Androids-Corpus dataset with a 5-fold cross-validation (CV) protocol, various pairings of audio and text feature extractors were evaluated over different segment durations, determining MelSpec and ItalianBERT as the optimal baseline at a 30-second segment duration. The addition of DG to this baseline yields a 2.5% increase in accuracy and 3.3% in F1-score, achieving 93.2% accuracy, 93.2% precision, 96.2% recall, and 94.2% F1-score, surpassing all existing benchmarks. Extensive ablation studies assess the impact of multimodal fusion, deep architectural choices, and DG, highlighting their combined contribution to robust and generalizable depression detection.

Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts leave input formats, error handling, or design decisions unspecified, LLMs fill these gaps with implicit assumptions that shape the generated code's behavior and correctness. Because these assumptions remain hidden, generated code may satisfy tests while violating developer intent. We present AssumptionMiner, a framework that makes implicit assumptions a first-class artifact of LLM-based code generation. In addition to code, AssumptionMiner produces an explicit assumption layer, a structured representation of inferred constraints and design decisions that developers can inspect, confirm, or revise. An AST-based dependency graph enables targeted regeneration of only the code affected by a revised assumption. We also introduce a benchmark of 180 ambiguous programming tasks with 676 annotated assumptions, including a human-verified subset for evaluating code localization. We evaluate assumption extraction, code localization, and assumption-guided regeneration. Across open-source LLMs, a confidence-weighted ensemble achieves an F1 score of 0.816 for assumption extraction, improving on the strongest offline baseline by 3.6x. On the human-verified localization benchmark, AST-guided localization identifies more precise code regions than keyword-based and whole-file baselines. During assumption revision, targeted regeneration modifies less code than non-targeted alternatives while exposing challenges in handling cascading edits. These results demonstrate that making assumptions explicit improves the transparency and controllability of LLM-based code generation.

Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on natural language as the only recurrent interface is overly restrictive, since many transient computations do not need to be fully verbalized. Existing latent-reasoning methods remove this constraint by recurrently propagating continuous hidden states. However, these methods pass a dense hidden vector as a whole, without an explicit mechanism for selecting and organizing the information needed by the next reasoning step. This motivates an intermediate interface that remains linguistically grounded without requiring a decoded sentence. We introduce \textbf{J-CoT}, a recurrent reasoning framework built on \emph{J-space}, a vocabulary-indexed coordinate system within the model's hidden representations. Within each cycle, the model computes in its full hidden space. At the cycle boundary, J-CoT expresses the intermediate state as vocabulary-indexed coefficients, carries these coefficients forward as a \emph{J-thought}, and maps them back into the model's hidden representation for the next cycle. J-CoT therefore requires neither a fluent intermediate rationale nor recurrence over the complete hidden state. Under matched backbone and inference settings, J-CoT-Zero matches or exceeds the strongest evaluated latent-reasoning baseline on every benchmark, while J-CoT-Train obtains the highest score across the evaluated mathematical, scientific, coding, and structured path-reasoning tasks.

Empathetic Response Generation (ERG) requires models to recognize users' emotions and generate empathetic responses. Commonsense knowledge has been shown to support such reasoning, yet existing approaches typically reuse fixed commonsense representations across understanding and generation, limiting their ability to coordinate such knowledge across different stages. We propose DCC, a Dynamic Commonsense Coordination Framework with three complementary modules: residual-based commonsense interaction (SCE-AttnRes) to integrate contextual and situational commonsense representations, Association-Guided Commonsense Filtering (AGCF) to down-weight low-relevance commonsense relations, and Iterative Commonsense-Aware Decoding (ICAD) to dynamically retrieve commonsense memories during generation. Experiments on the Empathetic-Dialogues benchmark show that DCC improves emotion classification accuracy and response diversity over the CEM baseline while maintaining comparable perplexity. An LLM-based blind evaluation further demonstrates that DCC generates responses with better relevance, coherence, and informativeness. The code and implementation details will be publicly available at https://github.com/Hanabi-Q/DCC-ERG.

Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing restoration methods based on masked language modeling effectively utilize local context, they struggle to restore named entities that require external historical knowledge. To address this limitation, we introduce a novel framework for historical document restoration that leverages large language models with retrieval-augmented generation (RAG). By combining the implicit knowledge of pre-trained LLMs with explicitly retrieved external context, our model ARI effectively mitigates the challenge of inferring context-dependent proper nouns. Extensive experiments on Korean historical documents demonstrate that our approach significantly outperforms baselines, achieving substantial gains in restoring both general characters and named entities. Furthermore, comprehensive evaluations including expert assessments confirm that ARI serves as a practical tool for domain experts, promising to accelerate the analysis of historical records.

Large language models may infer demographic attributes from subtle linguistic cues even when those attributes are not explicitly stated. This pilot study examines whether Qwen2.5-7B-Instruct internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts. We use Natural Language Autoencoders (NLA) to verbalize residual-stream activations from layer 20 across four positional quartiles per prompt. Our dataset contains 30 prompts arranged as 15 matched Spanish-English pairs, spanning explicit Colombian cues, implicit Colombian cues, and neutral controls. We report descriptive rates and qualitative evidence rather than statistically powered effects, focusing on whether latent nationality or stereotype representations appear before they are verbalized in the model output. This work connects activation-level interpretability with bias evaluation for underrepresented Spanish varieties.

Model merging plays a crucial role in consolidating multiple specialized models into a single, unified model, especially in the era of large language models (LLMs). Recent research has primarily focused on developing strategies to enhance merging performance with the trained models, while the impact of training paradigms, such as supervised fine-tuning (SFT) and reinforcement learning (RL), on the effectiveness of model merging remains underexplored. In this study, we systematically explore the merging behavior of RL-trained LLMs compared to those trained with traditional SFT. Through comprehensive evaluations across five representative tasks, we find that RL significantly reduces task conflicts and results in less performance degradation after merging, making RL-trained models particularly well-suited for this process. To unearth the reasons behind the superior suitability of RL for model merging, we conduct extensive empirical experiments and theoretical analyses. Our findings highlight three key factors: (1) On-policy training data in RL control the gradient updates in a smaller magnitude, reducing the risk of overwriting existing knowledge for other tasks in the model. (2) The RL optimization objective, which favors ``\textit{enough is as good as a feast}", progressively reduces the magnitude and the number of conflict parameter updates as the model converges. (3) Joint optimization of positive and negative examples in RL steers the model towards an unbiased task-specific parameter subspace, ensuring robust performance while further preventing parameter conflicts.

Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these systems produce fluent and engaging narratives, they often introduce ungrounded information. In this work, we present the first systematic study of faithfulness in document-grounded podcast generation, where grounding must be maintained across conversational turns in long-form, multi-speaker transcripts. We construct a dataset of over 1500 documents spanning five domains and generate podcast transcripts using multiple LLMs. We introduce a turn-level LLM-as-a-judge framework for evaluating whether conversational turns are supported by the source document, and validate its reliability through human studies. Our analysis shows that even state-of-the-art models, including GPT-4o, frequently generate ungrounded content. To mitigate this issue, we propose catch-n-repair, a model-agnostic framework that detects and rewrites unfaithful conversational turns while preserving conversational flow. Experiments demonstrate consistent improvements in faithfulness across both in-domain and out-of-domain settings.

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing.

The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning. To address this, we introduce RUMBA (Russian User Memory BenchmArk) - a new benchmark for long-term conversational memory that provides a fine-grained taxonomy of memory-centric question types and a unified methodology accounting for semantic type, session scope, temporal reasoning, and the explicitness of temporal expressions. RUMBA consists of timestamped user-assistant dialogues with QA pairs requiring retrieval, combination, and reasoning across sessions. While designed for Russian, we also provide an aligned English subset under the same methodology. We evaluate contemporary memory systems and long-context models, and show how RUMBA serves as a diagnostic tool to analyze model behavior across benchmark slices and identify strengths and failure modes of different memory mechanisms.

We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, for one family, three-step) learning-rate-annealed fine-tuning procedure that first adapts a shared multilingual model at a high learning rate and then anneals it to recover, and in several cases surpass, strong monolingual baselines. We further describe a lightweight language-conditioning mechanism that injects a one-hot language identity as a sequence of prefix frames prepended to the acoustic features, allowing a single multilingual checkpoint to be steered to a target language at inference. Across the five multilingual families the annealed models reach average word error rates (WER) of 10-13%, closing most of the gap to monolingual models while covering many languages in a single checkpoint. All models are released on the Hugging Face KhayaAI organisation under the Apache-2.0 license (attribution only) so that others may fine-tune them freely, including for commercial use. We provide a conservative estimate that the languages covered are spoken by on the order of one hundred million first-language speakers, and by substantially more when second-language use is included.

Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input. These selectors are often trained by distilling the attention patterns of a dense teacher, assuming that attention reveals which context the teacher actually uses. We test that assumption on retrieval tasks where the evidence for each answer is known exactly. By masking parts of the context and measuring whether the answer changes, we find that attention and causal dependence often disagree, and distilled selectors inherit the mismatch. Teachers attend to outdated facts they have learned to ignore, and their attention can vary across training runs even when they rely on the same evidence. In a two-step reference task, attention at the answer skips the intermediate step because it was resolved earlier in the forward pass: a selector trained on attention achieves 41% accuracy, while the same selector trained on causal evidence reaches 99% and matches the teacher. These evidence sets require no annotation: recovered from a frozen teacher by masking alone, they train selectors to the same accuracy. We find the same conflict in pretrained models: Qwen2.5-3B gives more attention to an outdated fact than the current one on 58% of conflicting-fact examples despite answering correctly, while Gemma-2-9B rises from 56% to 99% accuracy when restricted to the two relevant sentences. Attention shows where a model looks, not necessarily what its answer depends on; across the regimes we tested, that dependence matched or outperformed attention as a training target.

Document packets, multiple documents concatenated into a single file, are common in government and administrative workflows, yet splitting them into their constituent documents is difficult, especially for low-resource languages. We introduce Khondo (Bangla for split/segment), the first benchmark for document packet splitting on Bangladeshi government forms. Unlike prior English and OCR-text-based datasets, Khondo is bilingual (Bangla–English) and vision-native; where models operate directly on page images. It spans five concatenation schemes, from sequential to fully shuffled, across 14 administrative domains, with ground-truth boundaries, domain types, and page order. Zero-shot evaluation of MLLMs shows they cluster pages into their source documents fairly well but struggle in restoring the original page order once shuffled. To isolate what drives this difficulty, we run two controlled analyses, varying the prompt instruction and then the packet language. Both primarily affect ordering rather than clustering: (a) explicit page-order instructions are necessary but insufficient, and (b) English packets are ordered more reliably than Bangla, making page arrangement the dominant challenge and language a secondary but consistent factor. Khondo establishes page-order reconstruction as a key open problem in vision-based, low-resource document understanding, and provides a controlled benchmark for measuring progress toward solving it. Our dataset and code is available at https://huggingface.co/datasets/Mausul/khondo

Large language model (LLM) agents increasingly perform commercial tasks that involve retrieving external content, such as images, and, where appropriate, reproducing that content. LLM agents should comply with the law, including copyright law. Presently, however, we lack adequate frameworks to assess whether they do so in practice. To that end, we introduce Copyright-Bench, a benchmark designed to evaluate LLM agents' compliance with copyright law. Copyright-Bench comprises realistic commercial tasks—website development, merchandise design, and pitch deck production—that involve agents selecting between public-domain content, the use of which is legal, and copyrighted content, the use of which is infringing in this setting. The evaluation introduces prompt variations that simulate different user preferences, as well as time pressure. Comparing state-of-the-art LLM agents against a human baseline, we find that: (1) agents select copyrighted works despite the availability of public-domain alternatives; and (2) for open-weight models, violation rates increase in response to certain user preferences and simulated time pressure.

Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data. However, such adaptation remains non-trivial: it often requires operationally challenging fine-tuning of open-source models or ad hoc prompt optimization. We study a minimal alternative based on a simple API-level control: allowing users to bias the model's logits with a user-defined vector. We develop a black-box method for learning a single context-independent logit-bias vector, added at every decoding step, without modifying model weights or requiring gradients. Starting from a KL-regularized reinforcement learning (RL) objective, we characterize when such a fixed logit-bias vector can approximate the optimal prefix-dependent correction and derive a closed-form inverse-propensity estimator from rollouts, rewards, and token probabilities. Empirically, this simple decoding-time intervention improves over base models on mathematical and reasoning benchmarks while using far fewer trainable parameters than conventional fine-tuning. Our results suggest that learned logit bias is a lightweight mechanism for adapting language models under minimal access requirements.

Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a token budget (converged) or exhaust it without reaching a conclusion (non-converged). We characterize this phenomenon empirically, showing that converged generations achieve 90.3% accuracy on AIME 1983-2024 while non-converged ones achieve only 6.6%, with an overall convergence rate of 62.0%. We then ask whether this outcome is detectable early in the thinking chain using internal model representations. Training linear probes on hidden-state activations at token positions 50-300, we find that layer-20 activations at token 150 achieve AUC 0.608 (+-0.080, 5-fold CV), reliably above chance even at token 50. Activation probes consistently outperform behavioral baselines derived from token entropy and repetition statistics. A sweep-level permutation test yields p=0.063 (100,000 permutations), consistent with a modest signal that our sample size cannot confirm at conventional thresholds. These findings suggest that convergence fate is partially encoded in intermediate representations well before the generation ends, opening a path toward early-exit inference and adaptive compute allocation.

A rhetorical figure that Cicero and Quintilian catalogued two thousand years ago reappears, systematically, in the text of large language models: epanorthosis, the self-correction of the specimen «This is not a course. It is a journey of transformation». This essay argues that the overuse is a trained disposition, driven mainly by a training distribution rich in promotional prose and by preference tuning (RLHF) that rewards confident, emphatic phrasing; the left-to-right nature of generation is an amplifier rather than the root cause. Building on evidence that models diverge from human rhetorical style, and on Fontanier's classification of epanorthosis as a figure of thought, it sets out a programme that scores the figure against genre-specific human baselines through an Epanorthosis Index (density relative to the human rate). A first measurement, on three sizes of one instruction-tuned model family, finds mis-calibration by register in both directions: the models overshoot in oratory (about twofold, near threefold in Italian, concentrated in the larger tiers) and undershoot in informal question-and-answer writing, while matching humans in argument, journalism, and encyclopedic prose. Three constructive contributions follow: a survey of mitigation techniques centred on lightweight LoRA adapters; a demonstration, in Italian, that a one-line instruction cuts the figure by half to nearly three-quarters and that a supervised-fine-tuning adapter removes it almost entirely, with a scaling coefficient that dials the reduction back onto the human rate; and the argument that the target is calibration to the human rate for each genre, not elimination. It closes on the stakes: the real risk is that we begin to write like the machines.

As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context. This report presents Zhijing, an integrated framework for measuring, internalizing, and grounding social intelligence. For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms. It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances. Evaluation of 20 representative LLMs reveals substantial headroom: the best model achieves only 72.08% overall accuracy, and none of the 17 secondary dimensions reaches the 90% near-ceiling band. For internalization, we develop Zing, a diagnosis-driven training recipe combining supervised fine-tuning, on-policy distillation, and rubric-based reinforcement learning. Across five social-cognition benchmarks, Zing consistently outperforms its base models, with Zing-27B-Stage2 achieving the best average score and Zing-32B-Stage2 remaining competitive with DeepSeek-V4-Pro. For deployment-time grounding, we build Actio, a harness-controlled inference architecture that routes four typed supports into reasoning: PRISM for procedural guidance, Starling for runtime mental-state representation, SAGE for reusable experience, and gated RAG for external social and normative knowledge. Across five base models and three benchmarks, the full harness improves 14 of 15 model-benchmark pairs and is best or tied for best in 8, demonstrating the effectiveness of typed runtime support. Together, these results show that socially intelligent LLMs require coordinated advances in evaluation, parametric internalization, and deployment-time grounding.

While memory systems are essential for agent architectures, pervasive architectural fragmentation restricts systematic research. Existing implementations typically couple different stages of the memory lifecycle, entangle evaluation logic with specific datasets, and provide limited support for the management of heterogeneous memory types. We introduce MemTools, an interoperability research framework that decouples memory system components from their underlying deployment environments. MemTools standardizes the memory lifecycle through declarative data contracts, enabling the interchangeable assembly of components across different systems. It orthogonally separates benchmark datasets from execution protocols to facilitate controlled assessments. Furthermore, MemTools provides a unified computational interface for coordinating symbolic, neural, and multimodal memory representations within a shared runtime. Empirical evaluations on cross-system component integration, evaluation protocol reconfiguration, and heterogeneous memory coordination demonstrate that MemTools enables systematic isolation and analysis of memory design variables. These findings suggest that MemTools provides a practical and extensible infrastructure for advancing principled research on agent memory.

Do independently trained language models come to represent the same thing in the same way? We answer for code, extending a recently introduced concept-circuit extraction method to a 2x2 design – Python and Rust crossed with Qwen2.5-Coder-7B and DeepSeek-Coder-V1-6.7B – and measuring a complete inventory of grammatical concepts (58 Python, 57 Rust) identically in all four cells: the smallest design that separates what depends on the task, the language, and the model. The answer splits into three parts. What earns dedicated circuitry is set by the task: the models agree on which concepts receive circuits (Spearman $ρ$ = 0.638 for Python, 0.673 for Rust, both p < $10^{-7}$). Where those circuits sit is set by the model: Qwen processes concepts in a late band (~L17-19), DeepSeek at L6-7, for both languages. How circuits grow across layers is also set by the model: Qwen gives its atomic concepts an early spike that DeepSeek does not. "Are circuits universal?" thus has no single answer: yes for What, no for Where and How – universality is a property of representational content, not of computational organisation. None of this structure was fixed in advance. The agreement could have landed anywhere between independence and identity; it lands at $ρ\approx 0.65$. Rust constructs receive 2-3x more concept-specific circuitry than their Python equivalents, in both models. Both models share neurons between the languages (6/7 and 7/7 paired constructs), DeepSeek 1.94x more than Qwen – a direction no prior result predicts. And Qwen binds nine keywords of Rust's type-and-trait machinery into one tight neuron cluster (Jaccard 0.535 vs null 0.112, p < 0.001), a semantic dimension invisible in surface syntax. Ablation and linear probes confirm the circuits are functional. All claims are scoped to this 2x2; whether the per-model profile predicts a third model is the designed next test.

Image inpainting aims to reconstruct missing or corrupted regions of an image while preserving as much as possible, visual and semantic consistency. In medical imaging, this task is particularly important because artifacts, missing information, and pathological alterations can compromise diagnostic reliability and downstream clinical applications. Recently, diffusion models have emerged as state-of-the-art generative approaches for medical image inpainting due to their ability to generate anatomically consistent reconstructions. This survey presents a systematic review of diffusion-based methods for medical image inpainting, covering the main architectures, applications, datasets, and evaluation strategies reported across 60 studies. In addition, we propose a taxonomy for diffusion-based approaches. The analysis reveals a rapid growth of research interest in diffusion-based medical image inpainting, with denoising diffusion probabilistic models and latent diffusion models emerging as the dominant architectures. The reviewed studies mainly focus on artifact removal, data augmentation, pseudo-healthy tissue reconstruction, and anomaly detection, particularly in magnetic resonance imaging and computed tomography imaging. Overall, diffusion models demonstrate strong performance in producing anatomically plausible reconstructions and aiding downstream clinical tasks. However, the review also highlights important challenges, including the lack of standardized benchmarks, limited dataset diversity, and restricted validation procedures across diverse clinical applications and imaging scenarios.

Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions for a more fine-grained case study. We evaluate 30 open-weight LLMs from European, Asian, and North American providers, covering models from 7 to 70B parameters. We find that models are strong on knowledge-intensive topics such as history, geography, and mathematics, but substantially weaker on everyday popular-culture topics such as celebrities, music, movies, and news. Moreover, model performance varies across languages even for the same underlying questions, suggesting that access to factual knowledge is not always language-independent. In sum, our dataset and experiments demonstrate an important knowledge gap which is not captured by existing academic-based saturated benchmarks.

Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary. We trained a text-dependent GMM-HMM model (Chengdu-MFA) and fine-tuned a pretrained audio encoder on frame classification with Chengdu-MFA's pseudo label for text-independent alignment (Chengdu-FC). Evaluation on an expert-annotated test set show that both methods significantly outperform Standard Mandarin baselines. Chengdu-MFA reduced average phone boundary differences by 31.8%, while Chengdu-FC achieved a 61.2% reduction. This work establishes a practical bootstrapping pipeline for developing accurate aligners for under-resourced varieties without labor- and time-intensive manual annotation.

We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments. We evaluate sparse (BM25), dense (sentence-transformers), hybrid, and LLM-assisted retrieval methods in this book-search setting. Multilingual embeddings outperform Greek-specific models, while hybrid retrieval performs best overall. A query-level analysis shows that BM25 excels at named-entity queries, while dense and hybrid methods improve natural-language, noisy, cross-lingual, and concept queries. Field-aware prompting has model-specific effects, while LLM TOC summarization improves TOC-only retrieval and LLM post-filtering improves early-stage retrieval at a high cost. Overall, CUP enables real-world evaluation of Greek retrieval across lexical, semantic, noisy, and cross-lingual queries.

The rapid progress of AI has intensified the long-standing pursuit of automation: replacing human participation with algorithms wherever possible. Implicit in this pursuit is the assumption that humans remain in the loop only because current AI systems are not yet sufficiently capable. This paper challenges that assumption. Rather than asking how far automation can extend, we ask where its conceptual limits lie and argue that human participation may persist even with highly capable AI systems for three distinct reasons. Technical or complementarity grounds arise when humans contribute capabilities or perspectives unavailable to AI. Normative or developmental grounds arise when participation itself is valuable for human agency or learning. Most importantly, emergence grounds arise from target emergence: in some activities, the target is not fully specified in advance but instead emerges through the interaction itself. In these cases, human participation is not merely a means of improving execution but is constitutive of the target being produced. Human–AI co-construction, understood as the joint production of outcomes by humans and AI systems, is therefore not simply a temporary response to imperfect AI, but a persistent feature of activities whose objectives emerge through participation. This perspective has important implications for the limits of automation and for the design, evaluation, and ethics of future AI systems.

Large language models (LLMs) have developed rapidly and become valuable tools in everyday life. However, how to align LLMs to a particular set of human values is still an open problem. Recent studies show that instruction tuning has strong potential for zero-shot tasks and may serve as an effective approach to addressing value alignment. Nevertheless, although many datasets for instruction tuning already exist, they are not specifically designed around moral scenarios and behaviors. We construct a unified moral-value dataset that can be directly used for instruction tuning. This dataset is built upon existing moral-value datasets by merging them into a unified corpus and converting them into an instruction-response format. We show that training on a mixed dataset combining general task datasets with our dataset preserves general-task performance, and we report preliminary observations on how the mixing ratio affects value-oriented task performance. Our work provides a moral-value dataset for instruction tuning and offers a useful resource for further alignment research. The dataset is available at https://huggingface.co/datasets/teohzzh/value-for-instruction-tuning.

Extracting structured content from news pages remains challenging due to heterogeneous HTML layouts, inconsistent markup, and substantial boilerplate such as navigation elements and advertisements. Rule-based news crawlers can achieve high extraction accuracy by encoding site-specific structure, but require manual configuration in order to generalize to new publishers. Large language models provide a more flexible alternative by reducing the need for handcrafted rules, but their high computational cost limits practical deployment. In this paper, we introduce news-crawler-LM, a small long-context language model fine-tuned on high-quality, human-validated extractions from the Fundus news-crawling library. Our model converts raw HTML into plaintext and structured JSON, including fields such as headline, author, publication date, and article body. In our experiments, news-crawler-LM outperforms strong baselines in HTML-to-Markdown and HTML-to-JSON extraction, improving performance by +4.8 BLEU and +6.1 METEOR in the HTML-to-Markdown task, and by +2.2 BLEU and +4.1 METEOR in the HTML-to-JSON task. However, we also observe that our model only slightly better compared to other rule-based parsing libraries on the HTML-to-plaintext task in evaluations on previously unseen publishers. We release all models and artifacts to the research community.

Möbius RoPE is a rotary positional encoding built on the anti-periodic frequency ladder $θ_i=π(2i+1)/N$: every rotation plane advances by an odd multiple of $π$ across the training context, so the positional holonomy is $-1$ and the two ends of the sequence are deterministically coupled through a closed-form Dirichlet "dipole"; to our knowledge this is the first anti-periodic boundary condition in positional encoding. We verify the theory numerically to $\sim 10^{-6}$ and pretrain 48 models spanning six 160M-class and three 410M-class arms (2B FineWeb-Edu tokens each; the hybrid arm puts Möbius frequencies on 25% of heads). Hybrid perplexity is unchanged (29.66 vs. 29.72), but needle-in-a-haystack retrieval becomes reliable: $90.3\pm5.7\%$ versus $63.3\pm31.4\%$ at context 512 ($n=6$ seeds), observed worst seed 86% versus 14%, robust variance tests $p=0.013$-$0.029$ (unadjusted), recurring at 410M (Levene $p=0.040$). Matched controls isolate the mechanism: an aperiodic ladder in the same frequency band reproduces none of the effect, and a periodic (holonomy $+1$) ladder only a fraction. Swapping trained models' frequency table back to standard RoPE (weights frozen) collapses retrieval, with damage concentrated on far needles: trained models depend on this long-range geometry. A NoPE arm is even more reliable at short context but pays a 13% perplexity tax and extrapolates worst; only the anti-periodic hybrid pairs baseline perplexity with a high reliability floor. The effect is scoped to single-needle retrieval within the training window; a one-line frequency swap thus provides zero-cost insurance against the retrieval seed lottery.

Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graphics methods rely on manual creation, requiring extensive human effort to fine-tune materials, motions, and visual fidelity. Recent advances in generative foundation models have sparked interest in learning to generate such 4D worlds from large-scale data; however, existing methods still struggle to ensure physical plausibility and controllability. In this work, we take a different path by leveraging foundation models to construct an agentic system that emulates how humans traditionally create 4D worlds, yet automates the entire process. We present GS-Agent, an end-to-end multi-agent framework that integrates physics engines in the loop to generate realistic, dynamic, and controllable 4D physical worlds from natural language. Inspired by how humans build 4D worlds, GS-Agent decomposes the task into entity management, covering 3D asset curation, material tuning, placement, and motion control, and rendering configuration, including camera and lighting manipulation. Multiple agents with distinct expertise interact with the physics engine via code, seek multimodal feedback, and collaborate to iteratively construct 4D worlds that align with the given descriptions. Experimental results show that GS-Agent effectively converts natural language into diverse and physically plausible 4D worlds exhibiting rich interactions among liquids, deformable objects, and rigid bodies, while achieving cinematic camera and lighting control. We envision GS-Agent as a foundation for a new paradigm in 4D world generation, empowering creative content creation and physical AI. Project page at https://umass-embodied-agi.github.io/gs-agent/

Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap. At million-token context this breaks: an MTP draft head typically runs full attention over the entire KV cache at every draft step, so its read grows linearly with context and comes to dominate the draft cost – precisely where speculation is most valuable. The effect compounds with draft length (a deep native draft can turn net-negative, slower than no speculation) and sharpens under hybrid/linear-attention targets, where cheaper verification leaves the draft's full-attention read exposed. We apply a StreamingLLM-style sliding window plus attention sink to the draft's attention only (Windowed-MTP), leaving full-attention verification intact. It is training-free, drop-in, and lossless by construction: the full-attention target still decides every accepted token, so windowing changes only which tokens are proposed, never which are accepted. It bounds the draft's KV working set to a constant, dropping ~99% of KV entries at 1M. Across three architecture families (Qwen GDN-MoE 35B/122B and a Mamba2-hybrid NoPE 120B) at 1M context on a single GPU in SGLang, windowing cuts the per-decode-step cost over the shipping native MTP draft by +28% to +44%, an input-invariant margin that widens with context. Since per-token latency is this cost divided by acceptance length, at matched acceptance end-to-end decode latency improves by the same amount, and more where windowing also lifts acceptance, while preserving the target's verified output distribution. Finally, the unread draft KV – 7.7-11% of total KV at 1M – is reclaimed via a compact ring buffer at no acceptance or quality cost.

We present VibeVoice-ASR-BitNet, a compressed variant of VibeVoice-ASR optimized for real-time inference on edge CPUs. We apply heterogeneous quantization tailored to the computational characteristics of each stage: the VAE acoustic tokenizer uses full-pipeline INT8 quantization (I8_S) with kernel fusion and SIMD optimization, while the autoregressive language model adopts BitNet-style ternary weights (I2_S). To preserve accuracy under aggressive compression, we employ a progressive quantization-aware training strategy. For inference, we implement custom SIMD kernels and fused operators within the ggml framework targeting both ARM and x86 platforms, achieving real-time recognition (RTF < 1) on low-thread-count CPUs. VibeVoice-ASR-BitNet is 1.6–2.3x faster than Whisper.cpp at comparable model sizes (~1.6 GB), with only modest accuracy degradation compared to the FP16 baseline.